• Geomechanics and Engineering
• /
• v.33 no.2
• /
• pp.183-194
• /
• 2023

This study presents the prediction of the California bearing ratio (CBR) of coarse- and fine-grained soils using artificial intelligence technology. The group method of data handling (GMDH) algorithm, an artificial neural network-based model, was used in the prediction of the CBR values. In the design of the prediction models, various combinations of independent input variables for both coarse- and fine-grained soils have been used. The results obtained from the designed GMDH-type neural networks (GMDH-type NN) were compared with other regression models, such as linear, support vector, and multilayer perception regression methods. The performance of models was evaluated with a regression coefficient (R²), root-mean-square error (RMSE), and mean absolute error (MAE). The results showed that GMDH-type NN algorithm had higher performance than other regression methods in the prediction of CBR value for coarse- and fine-grained soils. The GMDH model had an R² of 0.938, RMSE of 1.87, and MAE of 1.48 for the input variables {G, S, and MDD} in coarse-grained soils. For fine-grained soils, it had an R² of 0.829, RMSE of 3.02, and MAE of 2.40, when using the input variables {LL, PI, MDD, and OMC}. The performance evaluations revealed that the GMDH-type NN models were effective in predicting CBR values of both coarse- and fine-grained soils.

• Nuclear Engineering and Technology
• /
• v.55 no.3
• /
• pp.1105-1117
• /
• 2023

In this study, the pressure drop behavior of single- and two-phase flows of air and water through the porous beds filled with uniform and non-uniform sized spherical particles was examined. The pressure drop data in the single-phase flow experiments for the uniform particle beds agreed well with the original Ergun correlation. The results from the two-phase flow experiments were analyzed using numerical results based on three types of previous models. In the experiments for the uniform particle beds, the data on the two-phase pressure drop clearly showed the effect of the flow regime transition with a variation in the gas flow rate under stagnant liquid condition. The numerical analyses indicated that the predictability of the previous models for the experimental data relied mainly on the sub-models of the flow regime transitions and interfacial drag. In the experiments for the non-uniform particle beds, the two-phase pressure loss could be predicted well with numerical calculations based on the effective particle diameter. However, the previous models failed to accurately predict the counter-current flooding limit observed in the experiments. Finally, we propose a relation of falling liquid velocity into the particle bed by gravity to appropriately simulate the CCFL phenomenon.

• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.42.3-42.3
• /
• 2020

We investigate the observational properties of Wolf-Rayet stars, suggest the constraint of their mass-loss rate and apply our results to the observed progenitor candidates of Type Ib/Ic supernovae (iPTF13bvn and SN 2017ein). For this purpose, we adopt the WR star models with various mass-loss rates and wind terminal velocities. We obtain the high resolution spectra of those models at the pre-supernova phase using the radiative transfer code CMFGEN. We verify the optically faint property of SN Ic progenitors and show that the optical faintness is mainly originated by the high effective temperature at the photosphere. We also show that a simple analytic model for WR winds using a constant opacity can roughly predict the photospheric parameters. We show that the change of the mass-loss rate and the terminal wind velocity critically affects the optical luminosity. We find the optical luminosities of SN Ic progenitor models with our fiducial mass-loss rate prescription are fainter than the detection limits. We also suggest the mass-loss rate of WR stars may not exceed 2 times of our fiducial value by comparing our predictions with the detection limit of SN Ib/Ic progenitors. The directly observed progenitor candidate of iPTF13bvn can be explained by our SN Ib progenitor models. We find that the SN 2017ein progenitor candidate is too bright and too blue to be a SN Ic progenitor.

• Clinical and Experimental Vaccine Research
• /
• v.12 no.4
• /
• pp.291-297
• /
• 2023

Enterovirus infections induce infectious diseases in young children, such as hand, foot, and mouth disease which is characterized by highly contagious rashes or blisters around the hands, feet, buttocks, and mouth. This predominantly arises from enterovirus A71 or coxsackievirus A16 infections and in severe cases, they can lead to encephalitis, paralysis, pulmonary edema, or even fatality, representing a global health threat. Due to the absence of effective therapeutic strategies for these infections, various experimental animal models are being investigated for the development of vaccines. During the early stages of research on enterovirus infections, non-human primate infections exhibited symptoms like those in humans, leading to their utilization as model animals. However, due to economic and ethical considerations, their current usage is limited. While enterovirus infections do not readily occur in mice, an infection model with mouse-adapted strain in neonatal mice has been employed. Cellular receptors have been identified in human cells, and genetically modified mice expressing these receptors have been used. Most recently, the utilization of Mongolian gerbil model is actively being considered and should be pursued for further animal model development. So, herein, we provide a summarized overview of the current portfolio of available enterovirus infection models, emphasizing their respective advantages and limitations.

• Journal of Korea Artificial Intelligence Association
• /
• v.2 no.1
• /
• pp.7-14
• /
• 2024

In this paper, we explore the application of RNA-sequencing data and ensemble machine learning to predict lung cancer and treatment strategies for lung cancer, a leading cause of cancer mortality worldwide. The research utilizes Random Forest, XGBoost, and LightGBM models to analyze gene expression profiles from extensive datasets, aiming to enhance predictive accuracy for lung cancer prognosis. The methodology focuses on preprocessing RNA-seq data to standardize expression levels across samples and applying ensemble algorithms to maximize prediction stability and reduce model overfitting. Key findings indicate that ensemble models, especially XGBoost, substantially outperform traditional predictive models. Significant genetic markers such as ADGRF5 is identified as crucial for predicting lung cancer outcomes. In conclusion, ensemble learning using RNA-seq data proves highly effective in predicting lung cancer, suggesting a potential shift towards more precise and personalized treatment approaches. The results advocate for further integration of molecular and clinical data to refine diagnostic models and improve clinical outcomes, underscoring the critical role of advanced molecular diagnostics in enhancing patient survival rates and quality of life. This study lays the groundwork for future research in the application of RNA-sequencing data and ensemble machine learning techniques in clinical settings.

• Journal of Korean Society on Water Environment
• /
• v.40 no.4
• /
• pp.179-194
• /
• 2024

Biophysicochemical processes in water environments and treatment systems have been great concerns of engineers and scientists for controlling the fate and transport of contaminants. These processes are practically formulated as mathematical models written in coupled differential equations. However, because these process-based mathematical models consist of a large number of model parameters, they are complicated in analytical or numerical computation. Users need to perform substantial trials and errors to achieve the best-fit simulation to measurements, relying on arbitrary selection of fitting parameters. Therefore, this study adopted a Bayesian calibration method to estimate best-fit model parameters in a systematic way and evaluated the applicability of the calibration method to biophysicochemical processes of water environments and treatment systems. The Bayesian calibration method was applied to the microbial growth-decay kinetics and flocculation kinetics, of which experimental data were obtained with batch kinetic experiments. The Bayesian calibration method was proven to be a reasonable, effective way for best-fit parameter estimation, demonstrating not only high-quality fitness, but also sensitivity of each parameter and correlation between different parameters. This state-of-the-art method will eventually help scientists and engineers to use complex process-based mathematical models consisting of various biophysicochemical processes.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.9
• /
• pp.724-731
• /
• 2016

As the structural damage caused by earthquakes has been gradually increasing, estimating the seismic fragility of structures has become essential for earthquake preparation. Seismic fragility curves are widely used as a probabilistic indicator of structural safety against earthquakes, and many researchers have made efforts to develop them in a more accurate and effective manner. However, most of the previous research studies used simplified 2D analytical models when deriving fragility curves, mainly to reduce the numerical simulation time; however, in many cases 2D models are inadequate to accurately evaluate the seismic behavior of a structure and its seismic vulnerability. Thus, this study provides a way to derive more accurate, but still effective, seismic fragility curves by using 3D analytical models. In this method, the reliability analysis software, FERUM, is integrated with the structural analysis software, ZEUS-NL, enabling the automatic exchange of data between these two software packages, and the first order reliability method (FORM), which is not a sampling-based method, is utilized to calculate the structural failure probabilities. These tools make it possible to conduct structural reliability analyses effectively even with 3D models. By using the proposed method, this study conducted a seismic vulnerability assessment of RC frame structures with their 3D analytical models.

• Proceedings of the SAREK Conference
• /
• 2004.06a
• /
• pp.147-147
• /
• 2004

• Journal of the Korean School Mathematics Society
• /
• v.4 no.1
• /
• pp.9-27
• /
• 2001

The purpose of this study is to develop effective models for performance assesment in the subject of mathematics, In this study, a procedural model was created through selecting five evaluation methods that are the most relevant to evaluate mathematics comprehension. Also this study provides the application of procedural model over the span of an academic semester.

• The Journal of Economics, Marketing and Management
• /
• v.12 no.3
• /
• pp.23-33
• /
• 2024

This study aims to enhance the accuracy of effective demand analysis for publicly supported private rental housing by integrating the RIR into the traditional Mankiw-Weil (MW) model. Traditional models like the M-W model, which account for household income, housing costs, and household size, often fall short in estimating demand driven by large-scale development projects. By integrating the RIR factor, this study introduces a more accurate and practical approach to analyzing effective housing demand. Findings show that the modified M-W model incorporating RIR predicts effective demand with greater precision than traditional methods. This advancement allows developers to plan projects more efficiently and aids governments and local authorities in implementing more effective housing policies. Furthermore, the study assesses the real housing cost burden on households, elucidating their capacity to pay housing costs based on household size and income quintile. This information enables policymakers to design targeted housing support policies for specific demographic groups. Additionally, the research provides comprehensive policy recommendations tailored to various regions and housing types. Overall, this study lays a vital groundwork for the long-term analysis of the effects of economic changes and housing market trends on effective demand.